© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203302
    Prev
    Next
    INDEX
    Explanations

    by reporter, writer, author, correspondent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    า
    0.73
    اً
    0.68
    ONE
    0.67
     CEOs
    0.66
    ركه
    0.66
    PC
    0.65
    രിൽ
    0.64
    jarige
    0.64
     rebels
    0.63
    li
    0.62
    POSITIVE LOGITS
    ها
    0.84
    ed
    0.75
    de
    0.75
    た
    0.75
    リ
    0.75
    리
    0.73
    ول
    0.71
    ad
    0.70
    _
    0.70
    ام
    0.69
    Activations Density 0.000%

    No Known Activations